{
  "best_global_step": 5078,
  "best_metric": 0.9431434869766235,
  "best_model_checkpoint": "/kaggle/working/checkpoint-5078",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5078,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 166.75547790527344,
      "learning_rate": 3.3736310523828036e-05,
      "loss": 21.1932,
      "step": 5078
    },
    {
      "epoch": 1.0,
      "eval_model_preparation_time": 0.0019,
      "eval_runtime": 171.0869,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "eval_validation_eval_cosine_accuracy": 0.9431434869766235,
      "step": 5078
    }
  ],
  "logging_steps": 500,
  "max_steps": 15234,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}